Add HEAD route for remotes and gems remote type (#148)

Remotes answer only GET, so HEAD probes get 405, and there is no RubyGems remote. Synthesized (github_*) and rewritten (npm, helm, pypi, puppet, terraform, nuget) mutable responses need the GET path for HEAD lengths to match.

- add a HEAD route for /api/v1/remote/{name}/*; rewritten and synthesized mutable HEADs go through the GET path
- mark rewriting providers with a ResponseRewriter capability; set Content-Length on proxied GETs
- use the remote's upstream client for upstream HEAD
- add a gems remote type: compact index and specs mutable, .gem and gemspec immutable
- add gems docs, UI snippet and e2e caching case; add HEAD-vs-GET e2e checks

Reviewed-on: #148
Co-authored-by: unkin-agent <unkin-agent@unkin.net>
Co-committed-by: unkin-agent <unkin-agent@unkin.net>

internal/api/v1/proxy.go

@@ -42,6 +42,7 @@ func NewProxyHandler(engine *proxy.Engine, virtualEngine *virtual.Engine, db *da
 func (h *ProxyHandler) Routes() chi.Router {
 	r := chi.NewRouter()
 	r.Get("/remote/{remoteName}/*", h.handleProxy)
+	r.Head("/remote/{remoteName}/*", h.handleProxyHead)
 	r.Get("/local/{localName}/*", h.handleLocal)
 	r.Put("/local/{localName}/*", h.handleLocalPut)
 	r.Get("/virtual/{virtualName}/*", h.handleVirtual)
@@ -70,31 +71,43 @@ func (h *ProxyHandler) handleDockerPing(w http.ResponseWriter, r *http.Request)
 	w.WriteHeader(http.StatusOK)
 }
 
-func (h *ProxyHandler) handleProxy(w http.ResponseWriter, r *http.Request) {
+// remoteFor resolves the remote and provider named in the request, writing the
+// error response itself when either is missing.
+func (h *ProxyHandler) remoteFor(w http.ResponseWriter, r *http.Request) (*models.Remote, provider.Provider, bool) {
 	remoteName := chi.URLParam(r, "remoteName")
-	path := chi.URLParam(r, "*")
-
 	remote, err := h.db.GetRemote(r.Context(), remoteName)
 	if err != nil {
 		http.Error(w, fmt.Sprintf("remote %q not found", remoteName), http.StatusNotFound)
-		return
+		return nil, nil, false
 	}
-
 	prov, err := provider.Get(remote.PackageType)
 	if err != nil {
 		http.Error(w, fmt.Sprintf("no provider for %q", remote.PackageType), http.StatusInternalServerError)
+		return nil, nil, false
+	}
+	return remote, prov, true
+}
+
+// serveRemote lets metadata-only remotes (e.g. github_rpm) synthesize their own
+// responses and redirect package downloads instead of proxying bytes.
+func (h *ProxyHandler) serveRemote(w http.ResponseWriter, r *http.Request, remote *models.Remote, prov provider.Provider, path string) bool {
+	rs, ok := prov.(provider.RemoteServer)
+	return ok && rs.ServeRemote(w, r, *remote, path, fmt.Sprintf("%s://%s", scheme(r), r.Host), h.db)
+}
+
+func (h *ProxyHandler) handleProxy(w http.ResponseWriter, r *http.Request) {
+	remote, prov, ok := h.remoteFor(w, r)
+	if !ok {
 		return
 	}
-
-	// Metadata-only remotes (e.g. github_rpm) synthesize their own responses and
-	// redirect package downloads to a backend remote instead of proxying bytes.
-	if rs, ok := prov.(provider.RemoteServer); ok {
-		proxyBaseURL := fmt.Sprintf("%s://%s", scheme(r), r.Host)
-		if rs.ServeRemote(w, r, *remote, path, proxyBaseURL, h.db) {
-			return
-		}
+	path := chi.URLParam(r, "*")
+	if h.serveRemote(w, r, remote, prov, path) {
+		return
 	}
+	h.serveFetch(w, r, remote, prov, path)
+}
 
+func (h *ProxyHandler) serveFetch(w http.ResponseWriter, r *http.Request, remote *models.Remote, prov provider.Provider, path string) {
 	result, err := h.engine.Fetch(r.Context(), *remote, path, prov, r.Header)
 	if err != nil {
 		var proxyErr *proxy.ProxyError
@@ -102,7 +115,7 @@ func (h *ProxyHandler) handleProxy(w http.ResponseWriter, r *http.Request) {
 			http.Error(w, proxyErr.Message, proxyErr.Status)
 			return
 		}
-		slog.Error("proxy fetch failed", "remote", remoteName, "path", path, "error", err)
+		slog.Error("proxy fetch failed", "remote", remote.Name, "path", path, "error", err)
 		http.Error(w, "bad gateway", http.StatusBadGateway)
 		return
 	}
@@ -122,25 +135,33 @@ func (h *ProxyHandler) handleProxy(w http.ResponseWriter, r *http.Request) {
 	w.Header().Set("Content-Type", result.ContentType)
 	w.Header().Set("X-Artifact-Source", result.Source)
 	if result.Size > 0 {
+		w.Header().Set("Content-Length", fmt.Sprintf("%d", result.Size))
 		w.Header().Set("X-Artifact-Size", fmt.Sprintf("%d", result.Size))
 	}
 	w.WriteHeader(http.StatusOK)
 	io.Copy(w, body)
 }
 
-func (h *ProxyHandler) handleProxyHead(w http.ResponseWriter, r *http.Request) {
-	remoteName := chi.URLParam(r, "remoteName")
-	path := chi.URLParam(r, "*")
+func rewritesMutable(prov provider.Provider, path string) bool {
+	_, sr := prov.(provider.ServeRewriter)
+	_, rr := prov.(provider.ResponseRewriter)
+	return (sr || rr) && prov.Classify(path) == provider.Mutable
+}
 
-	remote, err := h.db.GetRemote(r.Context(), remoteName)
-	if err != nil {
-		http.Error(w, fmt.Sprintf("remote %q not found", remoteName), http.StatusNotFound)
+// handleProxyHead answers HEAD like GET without a body. Responses a provider
+// synthesizes or rewrites per request go through the GET path so their headers
+// match; everything else is answered from store metadata or an upstream HEAD.
+func (h *ProxyHandler) handleProxyHead(w http.ResponseWriter, r *http.Request) {
+	remote, prov, ok := h.remoteFor(w, r)
+	if !ok {
 		return
 	}
-
-	prov, err := provider.Get(remote.PackageType)
-	if err != nil {
-		http.Error(w, fmt.Sprintf("no provider for %q", remote.PackageType), http.StatusInternalServerError)
+	path := chi.URLParam(r, "*")
+	if h.serveRemote(w, r, remote, prov, path) {
+		return
+	}
+	if rewritesMutable(prov, path) {
+		h.serveFetch(w, r, remote, prov, path)
 		return
 	}
 
@@ -151,7 +172,7 @@ func (h *ProxyHandler) handleProxyHead(w http.ResponseWriter, r *http.Request) {
 			http.Error(w, proxyErr.Message, proxyErr.Status)
 			return
 		}
-		slog.Error("proxy head failed", "remote", remoteName, "path", path, "error", err)
+		slog.Error("proxy head failed", "remote", remote.Name, "path", path, "error", err)
 		http.Error(w, "bad gateway", http.StatusBadGateway)
 		return
 	}

internal/api/v1/routes_test.go

@@ -0,0 +1,41 @@
+package v1
+
+import (
+	"net/http"
+	"testing"
+
+	"github.com/go-chi/chi/v5"
+
+	"git.unkin.net/unkin/artifactapi/internal/provider"
+	"git.unkin.net/unkin/artifactapi/internal/provider/npm"
+	"git.unkin.net/unkin/artifactapi/internal/provider/nuget"
+	"git.unkin.net/unkin/artifactapi/internal/provider/rpm"
+)
+
+func TestRoutesRemoteHead(t *testing.T) {
+	r := (&ProxyHandler{}).Routes()
+	for _, m := range []string{http.MethodGet, http.MethodHead} {
+		if !r.Match(chi.NewRouteContext(), m, "/remote/myremote/some/path") {
+			t.Errorf("%s /remote/myremote/some/path not routed", m)
+		}
+	}
+}
+
+func TestRewritesMutable(t *testing.T) {
+	tests := []struct {
+		name string
+		prov provider.Provider
+		path string
+		want bool
+	}{
+		{"npm packument", &npm.Provider{}, "left-pad", true},
+		{"npm tarball", &npm.Provider{}, "left-pad/-/left-pad-1.3.0.tgz", false},
+		{"nuget index", &nuget.Provider{}, "index.json", true},
+		{"rpm repodata", &rpm.Provider{}, "repodata/repomd.xml", false},
+	}
+	for _, tc := range tests {
+		if got := rewritesMutable(tc.prov, tc.path); got != tc.want {
+			t.Errorf("%s: rewritesMutable = %v, want %v", tc.name, got, tc.want)
+		}
+	}
+}